Name: effect
Rating: 48.8 (1 reviews)
Author: XiaomiMiMo

Blog Docs Log inGet started

effect

Answer questions about the Effect framework

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/effect/SKILL.md

The canonical home for this skill is effect in XiaomiMiMo/MiMo-Code

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body establishes a sensible, lean verification-first workflow (clone the authoritative source, search it, answer from it — never from memory), which is the right shape for this skill. Its weaknesses are missing executable detail (no clone command, no check that the repo is already cloned) and absent validation checkpoints, leaving the reader to improvise the mechanics of each step.

Suggestions

Make the clone step executable: `git clone https://github.com/Effect-TS/effect-smol .opencode/references/effect-smol`, with a guard to skip if the directory already exists.

Add validation checkpoints, e.g. after cloning, confirm the repo is present before searching; and before answering, confirm each claim is backed by a cited file path from the cloned source.

Merge the 'Guidelines' section into the workflow (its bullets restate steps 2–3) and keep only the non-duplicative guidance such as 'cite specific files and patterns'.

Dimension	Reasoning	Score
Conciseness	The ~20-line body is lean with no concept padding, but 'a framework for writing typescript' is a mild over-explanation and the Guidelines section ('Always use the explore agent with the cloned repository...') restates workflow step 2, so it is 'efficient with minor instances that could be trimmed' rather than perfect.	4 / 5
Actionability	It supplies a concrete repo URL and destination path, but no executable command (e.g. `git clone <url> <path>`) and steps 2–3 ('Use the explore agent to search the codebase for answers', 'Provide responses based on the actual Effect source code') are high-level direction with key execution details missing — between anchors 3 and 4, closest to 3.	3 / 5
Workflow Clarity	The three numbered steps form a clear sequence, but there are zero checkpoints: nothing verifies the clone succeeded, that the repository already exists from a prior session, or that search results actually support the answer before responding. This matches 'steps listed but validation gaps'; the operation is read-only so the destructive/batch cap does not apply, but anchor 4 requires most checkpoints present.	3 / 5
Progressive Disclosure	Under 50 lines with no external file references needed, organized into two clear sections — eligible for the simple-skill exception. It falls short of 5 only because the 'Guidelines' section partially duplicates the workflow section and could be merged, a minor organization gap.	4 / 5
	Total	14 / 20 Passed

Description

41%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description correctly names a distinct niche but does no work beyond that: it states a single generic action and provides no trigger guidance or concrete capabilities. Users asking about Effect-TS idioms, schemas, or runtime patterns would not reliably surface this skill from the description alone.

Suggestions

Add a 'Use when...' trigger clause, e.g. 'Use when the user asks about Effect-TS, @effect/* packages, or functional-effect patterns in TypeScript.'

Enumerate concrete capabilities instead of the generic 'Answer questions', e.g. 'Explain Effect APIs (Effect, Schema, Layer, Fiber), trace patterns to source in effect-smol, and generate idiomatic Effect code.'

Include natural synonyms and package names users actually say — 'Effect-TS', 'effect-smol', '@effect/core', 'functional effects' — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('the Effect framework') but the only action is the generic 'Answer questions about'; no concrete capabilities are listed, matching the 'names the domain but actions are minimal or generic' anchor rather than any multi-action example.	2 / 5
Completeness	The 'what' is stated at domain level ('Answer questions about the Effect framework') but there is no 'Use when...' clause or any trigger guidance, which caps completeness at 3. It is not 4 because the 'when' is entirely absent rather than merely implicit, and not 2 because the 'what' is domain-specific rather than 'helps with documents'-level vague.	3 / 5
Trigger Term Quality	Only two generic keywords ('Effect framework', 'questions') appear; natural phrases users would actually say — 'Effect-TS', '@effect/*', 'functional effects', 'Effect schema' — are missing, fitting the anchor for one or two generic keywords.	2 / 5
Distinctiveness Conflict Risk	'The Effect framework' is a clear niche with minimal overlap risk against unrelated skills, but the sparse trigger phrasing gives it only minor-distinct status rather than the 'clear niche with distinct triggers' of a 5.	4 / 5
	Total	11 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: XiaomiMiMo/MiMo-Code
Path: .agents/skills/effect/SKILL.md
Commit: f0293bf

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.